# count items on columndomains_list = df['domains'].value_counts()# return first n rows in descending ordertop_domains = domains_list.nlargest(20)top_domains
Lista del top 20 de hashtags más usados y su frecuencia
Code
# convert dataframe column to listhashtags = df['hashtags'].to_list()# remove nan items from listhashtags = [x for x in hashtags ifnot pd.isna(x)]# split items into a list based on a delimiterhashtags = [x.split('|') for x in hashtags]# flatten list of listshashtags = [item for sublist in hashtags for item in sublist]# count items on listhashtags_count = pd.Series(hashtags).value_counts()# return first n rows in descending ordertop_hashtags = hashtags_count.nlargest(20)top_hashtags
# filter column from dataframeusers = df['mentioned_names'].to_list()# remove nan items from listusers = [x for x in users ifnot pd.isna(x)]# split items into a list based on a delimiterusers = [x.split('|') for x in users]# flatten list of listsusers = [item for sublist in users for item in sublist]# count items on listusers_count = pd.Series(users).value_counts()# return first n rows in descending ordertop_users = users_count.nlargest(20)top_users
# plot the data using plotlyfig = px.line(df, x='date', y='like_count', title='Likes over Time', template='plotly_white', hover_data=['text'])# show the plotfig.show()
Tokens
Lista del top 20 de los tokens más comunes y su frecuencia
Code
# load the spacy model for Portuguesenlp = spacy.load("pt_core_news_sm")# load stop words for SpanishSTOP_WORDS = nlp.Defaults.stop_words# Function to filter stop wordsdef filter_stopwords(text):# lower text doc = nlp(text.lower())# filter tokens tokens = [token.text for token in doc ifnot token.is_stop and token.text notin STOP_WORDS and token.is_alpha]return' '.join(tokens)# apply function to dataframe columndf['text_pre'] = df['text'].apply(filter_stopwords)# count items on columntoken_counts = df["text_pre"].str.split(expand=True).stack().value_counts()[:20]token_counts
pra 1013
bh 338
brasil 236
bolsonaro 234
lula 220
dia 213
esquerda 206
hoje 196
tá 194
gente 181
nao 177
pessoas 163
presidente 150
cara 149
kalil 145
deus 138
vei 126
pro 125
mundo 122
verdade 116
Name: count, dtype: int64
Hora
Lista de las 10 horas con más cantidad de tweets publicados
Code
# extract hour from datetime columndf['hour'] = df['date'].dt.strftime('%H')# count items on columnhours_count = df['hour'].value_counts()# return first n rows in descending ordertop_hours = hours_count.nlargest(10)top_hours
# selection of topicstopics = [3]keywords_list = []for topic_ in topics: topic = topic_model.get_topic(topic_) keywords = [x[0] for x in topic] keywords_list.append(keywords)# flatten list of listsword_list = [item for sublist in keywords_list for item in sublist]# use apply method with lambda function to filter rowsfiltered_df = df[df['text_pre'].apply(lambda x: any(word in x for word in word_list))]percentage =round(100*len(filtered_df) /len(df), 2)print(f"Del total de {len(df)} tweets de @nikolas_dm, alrededor de {len(filtered_df)} hablan sobre temas de género, es decir, cerca del {percentage}%")
Del total de 7035 tweets de @nikolas_dm, alrededor de 3282 hablan sobre temas de género, es decir, cerca del 46.65%
Code
# drop rows with 0 values in two columnsfiltered_df = filtered_df[(filtered_df.like_count !=0) & (filtered_df.retweet_count !=0)]# add a new column with the sum of two columnsfiltered_df['impressions'] = (filtered_df['like_count'] + filtered_df['retweet_count'])/2# extract year from datetime columnfiltered_df['year'] = filtered_df['date'].dt.year# remove urls, mentions, hashtags and numbersp.set_options(p.OPT.URL)filtered_df['tweet_text'] = filtered_df['text'].apply(lambda x: p.clean(x))# Create scatter plotfig = px.scatter(filtered_df, x='like_count', y='retweet_count', size='impressions', color='year', hover_name='tweet_text')# Update title and axis labelsfig.update_layout( title='Tweets talking about gender with most Likes and Retweets', xaxis_title='Number of Likes', yaxis_title='Number of Retweets')fig.show()